THE LANGUAGE OF THOUGHT

By Drew V. McDermott. 1977

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

On the Binding Problem in Artificial Neural Networks (2020, background): “Though it was originally conceived for language, many believe that the principle of compositionality applies equally (or even more so) to mental representations (Butler, 1995; Fodor, 1975).”
Relational inductive biases, deep learning, and graph networks (2018, background): “, 2012; (1)Whether this entails a “language of thought” (Fodor, 1975) is beyond the scope of this work.”
The Symbol Grounding Problem (1990, neutral): “According to Fodor and Pylyshyn, this is a severe limitation, because many of our behavioral capacities appear to be symbolic, and hence the most natural hypothesis about the underlying cognitive processes that generate them would be that they too must be symbolic.”
A Roadmap Towards Machine Intelligence (2015, background): “In particular, we are not making claims about the internal representations of the machine being based on an interpretable “language of thought” (Fodor, 1975).”
Multimodal Distributional Semantics (2013, background): “Harnard, in the original paper, is discussing formal symbols, such as those postulated in Fodor's " language of thought " (Fodor, 1975), rather than the words of a natural language.”
Routing Networks and the Challenges of Modular and Compositional Computation (2019, background): “…science, where the nature of cognitive task-specific modules and the implementation details of compositional computation have been highly debated [Fodor, 1975, 1983, Fodor and Pylyshyn, 1988, Touretzky and Hinton, 1988, Smolensky, 1988, i.a.].1 Among others, there are two notable early attempts…”
Rethinking eliminative connectionism. (1998, background): “Fundamental to the view of symbol-manipulation is a distinction between instances (tokens) and classes (types) (Fodor, 1975; Jackendoff, 1983; for discussions of connectionist approaches to types and tokens, see Mozer, 1991; Marcus, 1999).”
Word meaning in minds and machines (2020, background): “Since thought is not (or not solely) word-based (Fodor, 1975; Murphy, 2002), words must connect to concepts more generally.”
Linguistic determinism and the understanding of false beliefs. (2000, unknown): “This is a possibility that sounds attractive, as it preserves the idea that our representational structures are present without learning (Fodor, 1975, 1992).”
Evidence for knowledge-based category discrimination in infancy. (2002, unknown): “Such knowledge could either be innate (Fodor, 1975) or start to develop during the first year of life (Mandler, 1992).”
Human few-shot learning of compositional instructions (2019, background): “This example illustrates systematic compositionality, the algebraic capacity to understand and produce an inﬁnite number of utterances from known components (Chomsky, 1957; Montague, 1970; Fodor, 1975).”
Theory learning as stochastic search in the language of thought (2012, methodology): “We formalize this Universal Theory as a probabilistic generative grammar, essentially a probabilistic version of a language of thought (Fodor, 1975).”
The Intentional Stance. (1987, background): “(Fodor 1975) How did this new movement shrug off Ryle's attack so blithely?”
Sources of flexibility in human cognition: dual-task studies of space and language. (1999, background): “It has been argued that language cannot extend the range of nonverbal cognitive abilities, because language itself is learned, and its learning depends on the nonverbal cognitive abilities in question (Fodor, 1975).”
The Challenges of Scientific Literacy: From the viewpoint of second‐generation cognitive science (2006, unknown): “Recall that first-generation cognitive science typically assumed that language serves as a conduit for expressing already-formed ideas and does not contribute to thinking (Fodor, 1975; Levelt, 1989).”
A Rational Analysis of Rule-Based Concept Learning (2008, methodology): “Thus, contra Fodor (1998), we would not expect that the representational complexity of concepts need be reflected in response times.”